6G networks — signal loss has vision potential

Dropouts in high-frequency communications could provide useful data on the layout of the surrounding area.
16 November 2022

Hot prospect: researchers are already digging into opportunities for next-generation communications. Image credit: Shutterstock.

Broadband cellular networks such as 5G are great news for high-bandwidth, low-latency communications. They add to what’s possible over 4G by enabling use cases such as remote vehicle piloting and ramp up the potential for telesurgery. But, as users of 5G-enabled smartphones may have encountered, there’s a downside to the latest telecommunications infrastructure. And this is unlikely to change with 6G networks.

“In 6G, we talk about high-frequency bands like terahertz [THz],” said Walid Saad of Virginia Tech’s College of Engineering. “These high frequencies can deliver high rates and high bandwidth, but the problem is that the signals are susceptible to blockages — much more so than low frequencies. Those frequencies can be blocked by things like your arms moving, or someone standing in a room with you.”

Environmental sensing

Saad and his research partner, Harpreet Dhillon – also based at Virginia Tech in the US, have been awarded a $1 million grant from the National Science Foundation to improve things for mobile phone users. It turns out that the dropouts in high-frequency communications could provide useful data on the layout of the surrounding area.

“If a communication system fails because the signal is blocked, at sub-THz bands, we can still use that information to sense the environment and know that there was an obstacle in the first place,” said Saad. “Then, with both situational awareness and other side information — like a picture of the room — we can use that multimodal data to communicate better.”

The concept is still at an early stage, but – in principle – information from 5G and 6G networks could be fed into vision-guided systems to improve the picture. Operating in reverse, images – for example, from a smartphone’s cameras – could help to reconfigure the signal so that it was less susceptible to interference.

Artificial intelligence (AI) has been shown to be successful in extracting value from a vast array of data and the team plans to apply similar methods here. Collaborating with Mehdi Bennis – a researcher based at the University of Oulu in Finland – the group will investigate how images can benefit wireless data transmission. “If successful, this will help reduce some of the network costs for both vendors and consumers,” said Bennis.

As well as potentially improving next-generation 6G wireless communications, vision-guided systems (fed with optical images and telecoms data) could open the door to gaming environments that are more interactive. There’s no shortage of hype surrounding the so-called ‘metaverse’, but perhaps wireless signals – as a proxy for the surrounding environment – could enhance the experience for smartphone users. It gives developers another channel to explore without requiring users to wear a VR headset or smart glasses.

Outreach opportunity

The NSF funding has an outreach component to it, as well as funding the main scientific thrust of the investigations. The team plans to create a learning platform as part of its work, which will allow students to get hands-on and experience vision-guided communications directly.

Saad heads up the Network sciEnce, Wireless, and Security laboratory at Virginia Tech (known as ‘NEWS’ on campus). And the lab’s research topics are varied. It’s no surprise to see 6G wireless networks and AI & machine learning on the list of focus areas, but their expertise goes broader.

Other tech pursuits include blockchain-assisted data authentication for the internet of vehicles and federated learning for connected and autonomous vehicles (CAVs). Here, the researchers investigate the capacity of CAVs to learn from each other to develop a so-called ‘autonomous controller design’. By harnessing the knowledge of a group of vehicles, the team hopes to improve system performance compared with feedback controllers trained solely on a CAV’s local data.

Quantum communications networks

One of the reasons for the rise of 5G and 6G networks is the need to manage much larger amounts of data traffic. Autonomous vehicles equipped with RADAR, LiDAR, and multiple cameras generate huge amounts of information. Digital twins – another rising application in the industrial space – are becoming much more detailed thanks to realistic engineering models and live data feeds gathered from hundreds of sensors. And this too is driving advances in communications.

One proposal for handling massive volumes of data is to use quantum communications networks (QCNs) – another research theme being explored by Saad’s team. QCNs have a range of advantages, which includes unbreakable security and unique computing capabilities alongside the potential for higher data throughput. Before we get too carried away though, it should be said that many of these concepts are at a theoretical stage.

To inform future work, Saad and his colleague, Mahdi Chehimi, have prepared a paper on the topic dubbed ‘Physics-Informed Quantum Communication Networks: A Vision Towards the Quantum Internet’. As the two experts explain, their goal is to bridge the gap between the different research directions for designing QCNs adopted by classical communications and quantum physics communities.